Throw more AI at your problems
frontierai.substack.com
Throw more AI at your problems
1–10 of 59 posts
Re: Throw more AI at your problems
#2I'll stay out of the inevitable "You're just adding a band aid! What are you really trying to do?" discussion since I kind of see the author's point and I'm generally excited about applying LLMs and ML at more tasks.
One thing I've been thinking about is if an agent (or collection of agents) can solve a problem initially in a non-scalable way through raw inference, but then develop code to make parts of the solution cheaper to run.
For example, I want to scrape a collection of sites. The agent would at first apply the whole HTML to the context to extract the data (expensive but it works), but then there is another agent that sees this pipeline and says "hey we can write a parser for this site so each scrape is cheaper", and iteratively replaces that segment in a way that does not disrupt the overall task.
Re: Throw more AI at your problems
#3With the current state of "AI", this strikes me as a "I had a problem and used AI, now I have two problems" kind of situation in most cases.
Re: Throw more AI at your problems
#4We aren’t good at creating software systems from reliable and knowable components. A bit skeptical that the future of software is making a Rube Goldberg machine of black box inter-LLM communication.
Re: Throw more AI at your problems
#5RAG doesn’t necessarily give the best results. Essentially it is a technically elegant way to semantic context to the prompt (for many use cases it is over-engineered). I used to offer RAG SQL query generations on SQLAI.ai and while I might introduce it again, for most use cases it was overkill and even made working with the SQL generator unpredictable.
Instead I implemented low tech “RAG” or “data source rules”. It’s a list of general rules you can attach to a particular data source (ie database). Rules are included in the generations and work great. Examples are “Wrap tables and columns in quotes” or “Limit results to 100”. It’s simple and effective - I can execute the generate SQL again my DB for insights.
Re: Throw more AI at your problems
#6We aren’t good at creating software systems from reliable and knowable components. A bit skeptical that the future of software is making a Rube Goldberg machine of black box inter-LLM communication.
I'm pretty sure this is a satire post
Re: Throw more AI at your problems
#7YES (although i'm hesitant to even say anything because on some level this is tightly-guarded personal proprietary knowledge from the trenches that i hold quite dear). why aren't you spinning off like 100 prompts from one input? it works great in a LOT of situations. better than you think it does/would, no matter your estimation of its efficacy.
Re: Throw more AI at your problems
#8I wish this was funny but it’s not. We are doing this now. It has become like “because it’s got electrolytes” in our org.
Re: Throw more AI at your problems
#9I'll stay out of the inevitable "You're just adding a band aid! What are you really trying to do?" discussion since I kind of see the author's point and I'm generally excited about applying LLMs and ML at more tasks. One thing I've been thinking about is if an agent (or collection of agents) can solve a problem initially in a non-scalable way through raw inference, but then develop code to make parts of the solution…
What do you mean the patient is bleeding out? We just need to use more bandaids!
Re: Throw more AI at your problems
#10RAG doesn’t necessarily give the best results. Essentially it is a technically elegant way to semantic context to the prompt (for many use cases it is over-engineered). I used to offer RAG SQL query generations on SQLAI.ai and while I might introduce it again, for most use cases it was overkill and even made working with the SQL generator unpredictable. Instead I implemented low tech “RAG” or “data source rules”. It’…
Reminds how few years ago Tesla (if i remember - Karpaty) described that in Autopilot they started to extract the 3rd model and use it to explicitly apply some static rules.